© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31937
    Prev
    Next
    INDEX
    Explanations

    failure, injury, damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellaneous
    -0.79
    enen
    -0.77
    ugh
    -0.76
    ORIES
    -0.75
    ꕥ
    -0.74
    êtements
    -0.73
    ophyte
    -0.72
     demasiado
    -0.71
    PLE
    -0.71
    Ответы
    -0.71
    POSITIVE LOGITS
     problems
    2.47
     failure
    2.36
     failures
    2.05
     damage
    2.03
     injury
    1.98
     loss
    1.94
     errors
    1.91
     losses
    1.91
     violations
    1.89
     violation
    1.87
    Activations Density 0.624%

    No Known Activations